Search

The human liver exhibits variable characteristics and anatomical information, which is often ambiguous in radiological images. Machine learning can be of great assistance in automatically segmenting the liver in radiological images, which can be further processed for computer-aided diagnosis. Magnetic resonance imaging (MRI) is preferred by clinicians for liver pathology diagnosis over volumetric abdominal computerized tomography (CT) scans, due to their superior representation of soft tissues. The convenience of Hounsfield unit (HoU) based preprocessing in CT scans is not available in MRI, making automatic segmentation challenging for MR images. This study investigates multiple state-of-the-art segmentation networks for liver segmentation from volumetric MRI images. Here, T1-weighted (in-phase) scans are investigated using expert-labeled liver masks from a public dataset of 20 patients (647 MR slices) from the Combined Healthy Abdominal Organ Segmentation grant challenge (CHAOS). The reason for using T1-weighted images is that it demonstrates brighter fat content, thus providing enhanced images for the segmentation task. Twenty-four different state-of-the-art segmentation networks with varying depths of dense, residual, and inception encoder and decoder backbones were investigated for the task. A novel cascaded network is proposed to segment axial liver slices. The proposed framework outperforms existing approaches reported in the literature for the liver segmentation task (on the same test set) with a dice similarity coefficient (DSC) score and intersect over union (IoU) of 95.15 % and 92.10 % , respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Diagnosis is the most important step in treating and managing kidney cancer, requiring accurate identification, localization, and classification of tumor regions. The selection of appropriate surgical procedures for malignant cases is further based on tumor volume and relative severity. In recent years, machine-learning-based approaches have been proposed to localize, quantify, and stratify kidney tumors using contrast-enhanced computed tomography (CT) images. However, previous studies have largely neglected the integration of patient metadata with clinical images to better diagnose and guide surgical interventions. In the current study, we developed a combined clinical and image-based approach to classify kidney cancers using a publicly available dataset. We show that the inclusion of clinical features alongside medical images improves the performance of kidney tumor classification. We further used clinical data together with a machine-learning approach to predict the expected surgical procedure employed in individual kidney cancer patients. In addition to cancer stage and tumor volume, some surprisingly common demographic features were revealed to be key determinants of the surgical procedure later selected for nephrectomy. Kidney cancers are one of the most common malignancies worldwide. Accurate diagnosis is a critical step in the management of kidney cancer patients and is influenced by multiple factors including tumor size or volume, cancer types and stages, etc. For malignant tumors, partial or radical surgery of the kidney might be required, but for clinicians, the basis for making this decision is often unclear. Partial nephrectomy could result in patient death due to cancer if kidney removal was necessary, whereas radical nephrectomy in less severe cases could resign patients to lifelong dialysis or need for future transplantation without sufficient cause. Using machine learning to consider clinical data alongside computed tomography images could potentially help resolve some of these surgical ambiguities, by enabling a more robust classification of kidney cancers and selection of optimal surgical approaches. In this study, we used the publicly available KiTS dataset of contrast-enhanced CT images and corresponding patient metadata to differentiate four major classes of kidney cancer: clear cell (ccRCC), chromophobe (chRCC), papillary (pRCC) renal cell carcinoma, and oncocytoma (ONC). We rationalized these data to overcome the high field of view (FoV), extract tumor regions of interest (ROIs), classify patients using deep machine-learning models, and extract/post-process CT image features for combination with clinical data. Regardless of marked data imbalance, our combined approach achieved a high level of performance (85.66% accuracy, 84.18% precision, 85.66% recall, and 84.92% F1-score). When selecting surgical procedures for malignant tumors (RCC), our method proved even more reliable (90.63% accuracy, 90.83% precision, 90.61% recall, and 90.50% F1-score). Using feature ranking, we confirmed that tumor volume and cancer stage are the most relevant clinical features for predicting surgical procedures. Once fully mature, the approach we propose could be used to assist surgeons in performing nephrectomies by guiding the choices of optimal procedures in individual patients with kidney cancer. [ABSTRACT FROM AUTHOR]

Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of blood to function properly and meet its metabolic demand, a change in CBVF can be an indication of neurological diseases. Depending on the severity of the disease, the symptoms may appear immediately or may appear weeks later. For the early detection of neurological diseases, a classification model is proposed in this study, with the ability to distinguish healthy subjects from critically ill subjects. The TCD ultrasound database used in this study contains signals from the middle cerebral artery (MCA) of 6 healthy subjects and 12 subjects with known neurocritical diseases. The classification model works based on the maximal blood flow velocity waveforms extracted from the TCD ultrasound. Since the signal quality of the recorded TCD ultrasound is highly dependent on the operator's skillset, a noisy and corrupted signal can exist and can add biases to the classifier. Therefore, a deep learning classifier, trained on a curated and clean biomedical signal can reliably detect neurological diseases. For signal classification, this study proposes a Self-organized Operational Neural Network (Self-ONN)-based deep learning model Self-ResAttentioNet18, which achieves classification accuracy of 96.05% with precision, recall, f1 score, and specificity of 96.06%, 96.05%, 96.06%, and 96.09%, respectively. With an area under the ROC curve of 0.99, the model proves its feasibility to confidently classify middle cerebral artery (MCA) waveforms in near real-time. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals immensely suffer from several physiological artifacts, including electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) artifacts, which must be removed to ensure EEG's usability. This paper proposes a novel one-dimensional convolutional neural network (1D-CNN), i.e., MultiResUNet3+, to denoise physiological artifacts from corrupted EEG. A publicly available dataset containing clean EEG, EOG, and EMG segments is used to generate semi-synthetic noisy EEG to train, validate and test the proposed MultiResUNet3+, along with four other 1D-CNN models (FPN, UNet, MCGUNet, LinkNet). Adopting a five-fold cross-validation technique, all five models' performance is measured by estimating temporal and spectral percentage reduction in artifacts, temporal and spectral relative root mean squared error, and average power ratio of each of the five EEG bands to whole spectra. The proposed MultiResUNet3+ achieved the highest temporal and spectral percentage reduction of 94.82% and 92.84%, respectively, in EOG artifacts removal from EOG-contaminated EEG. Moreover, compared to the other four 1D-segmentation models, the proposed MultiResUNet3+ eliminated 83.21% of the spectral artifacts from the EMG-corrupted EEG, which is also the highest. In most situations, our proposed model performed better than the other four 1D-CNN models, evident by the computed performance evaluation metrics. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is commonly used in medical diagnosis and minimally invasive image-guided operations. During an MRI scan, the patient's electrocardiogram (ECG) may be required for either gating or patient monitoring. However, the challenging environment of an MRI scanner, with its several types of magnetic fields, creates significant distortions of the collected ECG data due to the Magnetohydrodynamic (MHD) effect. These changes can be seen as irregular heartbeats. These distortions and abnormalities hamper the detection of QRS complexes, and a more in-depth diagnosis based on the ECG. This study aims to reliably detect R-peaks in the ECG waveforms in 3 Tesla (T) and 7T magnetic fields. A novel model, Self-Attention MHDNet, is proposed to detect R peaks from the MHD corrupted ECG signal through 1D-segmentation. The proposed model achieves a recall and precision of 99.83% and 99.68%, respectively, for the ECG data acquired in a 3T setting, while 99.87% and 99.78%, respectively, in a 7T setting. This model can thus be used in accurately gating the trigger pulse for the cardiovascular functional MRI. [ABSTRACT FROM AUTHOR]

With an expectation of an increased number of revision surgeries and patients receiving orthopedic implants in the coming years, the focus of joint replacement research needs to be on improving the mechanical properties of implants. Head-stem trunnion fixation provides superior load support and implant stability. Fretting wear is formed at the trunnion because of the dynamic load activities of patients, and this eventually causes the total hip implant system to fail. To optimize the design, multiple experiments with various trunnion geometries have been performed by researchers to examine the wear rate and associated mechanical performance characteristics of the existing head-stem trunnion. The objective of this work is to quantify and evaluate the performance parameters of smooth and novel spiral head-stem trunnion types under dynamic loading situations. This study proposes a finite element method for estimating head-stem trunnion performance characteristics, namely contact pressure and sliding distance, for both trunnion types under walking and jogging dynamic loading conditions. The wear rate for both trunnion types was computed using the Archard wear model for a standard number of gait cycles. The experimental results indicated that the spiral trunnion with a uniform contact pressure distribution achieved more fixation than the smooth trunnion. However, the average contact pressure distribution was nearly the same for both trunnion types. The maximum and average sliding distances were both shorter for the spiral trunnion; hence, the summed sliding distance was approximately 10% shorter for spiral trunnions than that of the smooth trunnion over a complete gait cycle. Owing to a lower sliding ability, hip implants with spiral trunnions achieved more stability than those with smooth trunnions. The anticipated wear rate for spiral trunnions was 0.039 mm3, which was approximately 10% lower than the smooth trunnion wear rate of 0.048 mm3 per million loading cycles. The spiral trunnion achieved superior fixation stability with a shorter sliding distance and a lower wear rate than the smooth trunnion; therefore, the spiral trunnion can be recommended for future hip implant systems. [ABSTRACT FROM AUTHOR]

In this paper, a surface acoustic wave (SAW) sensor for hip implant geometry was proposed for the application of total hip replacement. A two-port SAW device was numerically investigated for implementation with an operating frequency of 872 MHz that can be used in more common radio frequency interrogator units. A finite element analysis of the device was developed for a lithium niobate (LiNBO3) substrate with a Rayleigh velocity of 3488 m/s on COMSOL Multiphysics. The Multiphysics loading and frequency results highlighted a good uniformity with numerical results. Afterwards, a hip implant geometry was developed. The SAW sensor was mounted at two locations on the implant corresponding to two regions along the shaft of the femur bone. Three discrete conditions were studied for the feasibility of the implant with upper- and lower-body loading. The loading simulations highlighted that the stresses experienced do not exceed the yield strengths. The voltage output results indicated that the SAW sensor can be implanted in the hip implant for hip implant-loosening detection applications. [ABSTRACT FROM AUTHOR]

Total hip replacement (THR) is a common orthopedic surgery technique that helps thousands of individuals to live normal lives each year. A hip replacement replaces the shattered cartilage and bone with an implant. Most hip implants fail after 10–15 years. The material selection for the total hip implant systems is a major research field since it affects the mechanical and clinical performance of it. Stress shielding due to excessive contact stress, implant dislocation due to a large deformation, aseptic implant loosening due to the particle propagation of wear debris, decreased bone remodeling density due to the stress shielding, and adverse tissue responses due to material wear debris all contribute to the failure of hip implants. Recent research shows that pre-clinical computational finite element analysis (FEA) can be used to estimate four mechanical performance parameters of hip implants which are connected with distinct biomaterials: von Mises stress and deformation, micromotion, wear estimates, and implant fatigue. In vitro, in vivo, and clinical stages are utilized to determine the hip implant biocompatibility and the unfavorable local tissue reactions to different biomaterials during the implementation phase. This research summarizes and analyses the performance of the different biomaterials that are employed in total hip implant systems in the pre-clinical stage using FEA, as well as their performances in in vitro, in vivo, and in clinical studies, which will help researchers in gaining a better understanding of the prospects and challenges in this field. [ABSTRACT FROM AUTHOR]

An intelligent insole system may monitor the individual's foot pressure and temperature in real-time from the comfort of their home, which can help capture foot problems in their earliest stages. Constant monitoring for foot complications is essential to avoid potentially devastating outcomes from common diseases such as diabetes mellitus. Inspired by those goals, the authors of this work propose a full design for a wearable insole that can detect both plantar pressure and temperature using off-the-shelf sensors. The design provides details of specific temperature and pressure sensors, circuit configuration for characterizing the sensors, and design considerations for creating a small system with suitable electronics. The procedure also details how, using a low-power communication protocol, data about the individuals' foot pressure and temperatures may be sent wirelessly to a centralized device for storage. This research may aid in the creation of an affordable, practical, and portable foot monitoring system for patients. The solution can be used for continuous, at-home monitoring of foot problems through pressure patterns and temperature differences between the two feet. The generated maps can be used for early detection of diabetic foot complication with the help of artificial intelligence. [ABSTRACT FROM AUTHOR]

Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients. [ABSTRACT FROM AUTHOR]

Problem—Since the outbreak of the COVID-19 pandemic, mass testing has become essential to reduce the spread of the virus. Several recent studies suggest that a significant number of COVID-19 patients display no physical symptoms whatsoever. Therefore, it is unlikely that these patients will undergo COVID-19 testing, which increases their chances of unintentionally spreading the virus. Currently, the primary diagnostic tool to detect COVID-19 is a reverse-transcription polymerase chain reaction (RT-PCR) test from the respiratory specimens of the suspected patient, which is invasive and a resource-dependent technique. It is evident from recent researches that asymptomatic COVID-19 patients cough and breathe in a different way than healthy people. Aim—This paper aims to use a novel machine learning approach to detect COVID-19 (symptomatic and asymptomatic) patients from the convenience of their homes so that they do not overburden the healthcare system and also do not spread the virus unknowingly by continuously monitoring themselves. Method—A Cambridge University research group shared such a dataset of cough and breath sound samples from 582 healthy and 141 COVID-19 patients. Among the COVID-19 patients, 87 were asymptomatic while 54 were symptomatic (had a dry or wet cough). In addition to the available dataset, the proposed work deployed a real-time deep learning-based backend server with a web application to crowdsource cough and breath datasets and also screen for COVID-19 infection from the comfort of the user's home. The collected dataset includes data from 245 healthy individuals and 78 asymptomatic and 18 symptomatic COVID-19 patients. Users can simply use the application from any web browser without installation and enter their symptoms, record audio clips of their cough and breath sounds, and upload the data anonymously. Two different pipelines for screening were developed based on the symptoms reported by the users: asymptomatic and symptomatic. An innovative and novel stacking CNN model was developed using three base learners from of eight state-of-the-art deep learning CNN algorithms. The stacking CNN model is based on a logistic regression classifier meta-learner that uses the spectrograms generated from the breath and cough sounds of symptomatic and asymptomatic patients as input using the combined (Cambridge and collected) dataset. Results—The stacking model outperformed the other eight CNN networks with the best classification performance for binary classification using cough sound spectrogram images. The accuracy, sensitivity, and specificity for symptomatic and asymptomatic patients were 96.5%, 96.42%, and 95.47% and 98.85%, 97.01%, and 99.6%, respectively. For breath sound spectrogram images, the metrics for binary classification of symptomatic and asymptomatic patients were 91.03%, 88.9%, and 91.5% and 80.01%, 72.04%, and 82.67%, respectively. Conclusion—The web-application QUCoughScope records coughing and breathing sounds, converts them to a spectrogram, and applies the best-performing machine learning model to classify the COVID-19 patients and healthy subjects. The result is then reported back to the test user in the application interface. Therefore, this novel system can be used by patients in their premises as a pre-screening method to aid COVID-19 diagnosis by prioritizing the patients for RT-PCR testing and thereby reducing the risk of spreading of the disease. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases are the most common causes of death around the world. To detect and treat heart-related diseases, continuous blood pressure (BP) monitoring along with many other parameters are required. Several invasive and non-invasive methods have been developed for this purpose. Most existing methods used in hospitals for continuous monitoring of BP are invasive. On the contrary, cuff-based BP monitoring methods, which can predict systolic blood pressure (SBP) and diastolic blood pressure (DBP), cannot be used for continuous monitoring. Several studies attempted to predict BP from non-invasively collectible signals such as photoplethysmograms (PPG) and electrocardiograms (ECG), which can be used for continuous monitoring. In this study, we explored the applicability of autoencoders in predicting BP from PPG and ECG signals. The investigation was carried out on 12,000 instances of 942 patients of the MIMIC-II dataset, and it was found that a very shallow, one-dimensional autoencoder can extract the relevant features to predict the SBP and DBP with state-of-the-art performance on a very large dataset. An independent test set from a portion of the MIMIC-II dataset provided a mean absolute error (MAE) of 2.333 and 0.713 for SBP and DBP, respectively. On an external dataset of 40 subjects, the model trained on the MIMIC-II dataset provided an MAE of 2.728 and 1.166 for SBP and DBP, respectively. For both the cases, the results met British Hypertension Society (BHS) Grade A and surpassed the studies from the current literature. [ABSTRACT FROM AUTHOR]

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder–Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively. [ABSTRACT FROM AUTHOR]